| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| HLE All Non-Easy | QA+ | Recovery Rate9.3 | 3 | 3mo ago | |
| HLE Med. + Hard | QA+ | Recovery Rate13.1 | 3 | 3mo ago | |
| GPQA MC All Non-Easy | QA | Recovery Rate13.6 | 3 | 3mo ago | |
| GPQA MC (Med. + Hard) | Bit-Limited Chain-of-Thought (BL-CoT) | Recovery Rate40 | 3 | 3mo ago | |
| HLE | Accuracy11.2 | 2 | 1mo ago |